Connect
Optimize
Secure
Browserbase MCP Server
for AI Agents
Production-ready Browserbase MCP server with extensible actions — plus built-in authentication, security, and optimized execution.
Browserbase MCP Server
Built by 
StackOne
StackOne 
Coverage
19 Agent Actions
Create, read, update, and delete across Browserbase — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Browserbase MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Browserbase tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Browserbase call.
Tools Discovery →What is the Browserbase MCP Server?
A Browserbase MCP server lets AI agents read and write Browserbase data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Browserbase MCP server ships with pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Browserbase MCP Tools and Actions
Every action from Browserbase's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Contexts
- Create Context
Create a new browser context.
- Get Context
Retrieve details of a specific context.
- Update Context
Update a browser context.
- Delete Context
Delete a browser context.
Session Downloads
- Get Session Downloads
Download all files from a session as a ZIP archive.
Get Downloads
- Get Download
Retrieve metadata for a specific download.
Delete Downloads
- Delete Download
Delete a specific download.
Extensions
- Get Extension
Retrieve details of an uploaded extension.
- Delete Extension
Delete an uploaded extension.
Projects
- List Projects
List all projects in the account.
- Get Project
Retrieve details of the current project.
Project Usages
- Get Project Usage
Retrieve usage statistics for the project.
Sessions
- Create Session
Create a new browser session.
- List Sessions
List all browser sessions for the project.
- Get Session
Retrieve details of a specific session.
- Update Session
Update a session to request release.
Session Logs
- Get Session Logs
Retrieve logs for a specific session.
Session Recordings
- Get Session Recording
Retrieve the recording for a specific session.
Session Debug URLs
- Get Session Debug URLs
Retrieve live debug URLs for a session.
Set Up Your Browserbase MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Browserbase in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More Developer Tools MCP Servers
Azure DevOps
172+ actions
Cloudflare
137+ actions
Bitbucket
134+ actions
Supabase
128+ actions
GitLab
125+ actions
Terraform
118+ actions
OneLogin
109+ actions
Browserbase MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Browserbase MCP Server FAQ
Browserbase MCP server vs direct API integration — what's the difference?
A Browserbase MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Browserbase. A Browserbase MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Browserbase at runtime. StackOne provides both.
How does Browserbase authentication work for AI agents?
Browserbase authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Browserbase account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Browserbase MCP tools vulnerable to prompt injection?
Yes — Browserbase MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Browserbase agent and how do I avoid it?
Context bloat happens when Browserbase tool schemas and API responses eat your Browserbase agent's memory, preventing it from reasoning effectively. A single Browserbase query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Browserbase agent can access?
Yes — you can limit which actions your Browserbase agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Browserbase MCP server?
Yes — you can create custom agent actions for your Browserbase MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Browserbase's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Browserbase MCP server?
Skip a Browserbase MCP server if your integration is purely software-to-software — direct Browserbase API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Browserbase actions at runtime.
What AI frameworks and AI clients does the StackOne Browserbase MCP server support?
The StackOne Browserbase MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.